122 results about "Gradient estimation" patented technology

The invention discloses an automatic driving test scene set optimization method, apparatus and device, and a storage medium. The method comprises the steps of generating a simulation scene file in an OpenSCENARIO format through preprocessing data; analyzing the simulation scene file through a teacher model, outputting a risk description text, receiving a scene feature vector and the risk description text through a student model, and outputting a failure probability; determining a comprehensive value index according to the failure probability, dynamically updating a scene library of automatic driving test scenes, collecting failure data in an AUT test, performing incremental fine tuning on the student model, and obtaining an optimized target test scene set; the problem of gradient estimation variance explosion caused by sparseness disasters can be effectively solved, the stability of model training is improved, the recognition capability of a rare long-tail failure scene is enhanced, the accuracy of failure probability prediction is improved, the judgment accuracy of the model to a boundary scene is improved, and the accuracy and comprehensiveness of scene value quantification are improved.

The invention relates to the technical field of road repair state monitoring, in particular to a road repair state monitoring method and system based on edge calculation. The method comprises the following steps: acquiring planning information of a repaired road, deploying 3D laser scanning vibration meters at a plurality of repairing points, collecting pavement vibration signals in different time periods, and performing disordered distribution time domain feature analysis to obtain a vibration signal disordered distribution time domain graph; then, structure weakening behavior simulation is carried out based on the graph, periodic structure weakening data is quantified, and a pavement water damage cumulative gradient is obtained through water damage cumulative gradient estimation; and finally, in combination with the periodic structure weakening data and the water damage cumulative gradient, carrying out service life evaluation on the restoration state, and sending an evaluation result to the terminal. According to the invention, the road repair state monitoring technology is optimized, so that the road repair state monitoring technology is more perfect.

The invention discloses a multi-robot fixed time cooperative hunting method and system based on a distributed time-varying optimization algorithm. The method comprises the following steps: establishing a dynamic model and a communication topological graph of a multi-robot system; the method comprises the following steps: converting a fixed time distributed hunting problem of a multi-robot system into a fixed time distributed time-varying optimization problem, and constructing a global objective function; designing a fixed time distributed gradient estimator, and enabling each robot to estimate gradient information of a system global objective function within fixed time in a distributed mode; designing a self-adaptive zero-order neural network which is used for approximating an inverse matrix of a Hessian matrix; and designing a fixed-time distributed time-varying optimization algorithm for the multi-robot system by adopting the gradient information of the global objective function estimated by the distributed gradient estimator in the step 3 and the inverse matrix of the Hessian matrix approximated by the adaptive zero-order neural network in the step 4, so that each robot encircles the dynamic target in the fixed time in a distributed mode. According to the invention, the multi-robot system is ensured to surround the moving target in a formation form within a fixed time.

The invention discloses a control method of a flat wire motor. The method comprises the following steps: constructing an optimal current instruction table taking a rotating speed and a torque as indexes; if the motor is in the dynamic working condition, directly looking up a table to obtain a current optimal current instruction; if in a steady-state working condition, performing online search by taking a table look-up result as an initial point: generating two-dimensional Bernoulli random disturbance, and sequentially applying positive and negative disturbances to the initial point; respectively measuring the input power under the two disturbances; according to the ratio of the positive and negative input power difference to the corresponding disturbance component, synchronously calculating gradient estimation vectors of the system input power to d-axis and q-axis current; according to a steepest descent method, the current instruction is updated in the reverse direction of the gradient, an optimal instruction enabling the input power to be minimized is obtained, and an inverter is driven to control a motor to operate. According to the method, through a hybrid control strategy combining dynamic table look-up and steady-state online search, the total loss minimization of the flat wire motor under all working conditions in consideration of alternating current copper loss is realized, and the rapidity of dynamic response is ensured.

The invention discloses a slope estimation method and device, equipment and a storage medium. The method comprises the steps that the current corresponding driving working condition of a vehicle is obtained; target limiting parameters matched with the driving working conditions are determined; performing limiting processing on the original acceleration difference value by using the target limiting parameter to obtain a target acceleration difference value; the original acceleration difference value is the difference value between the detection acceleration and the motion acceleration of the vehicle, the detection acceleration is obtained through detection of an acceleration sensor arranged on the vehicle, and the motion acceleration is determined based on the vehicle speed; and estimating the gradient of the road where the vehicle is currently located by using the target acceleration difference value. In this way, the accuracy of road slope estimation can be improved.

The embodiment of the invention provides a large language model optimization method based on variance reduction and momentum acceleration. The method comprises the following steps: a gradient estimation stage of a large language model: initializing a seed list and a projection list; executing multiple independent query iterations, calling a disturbance subprogram, generating a random seed for the large language model, and storing a table; in the disturbance subprogram, the determined gradient projection value is stored in a projection list, and iteration is carried out for next query; after executing multiple independent query iterations, storing a plurality of random seeds and a plurality of gradient projection values corresponding to the random seeds; in the weight updating stage of the large language model, a gradient norm subprogram is called for each layer of the large language model, and a random seed is obtained to reset a random number generator; and determining variance-reduced gradient estimation according to the gradient projection value extracted from the projection list and the reproduced disturbance vector. According to the embodiment of the invention, gradient information queried for multiple times is aggregated to generate low-noise gradient estimation, and fine tuning of a large language model is completed.

The invention relates to the field of generative artificial intelligence image processing, and provides an initial noise distribution optimization method, device, equipment, medium and program, and the method comprises the steps: taking a denoising process as a fixed mapping relation, creating a trainable distribution parameter, and constructing a distribution parameter updating formula based on the fixed mapping relation; constructing a dynamic reward calibration module, calculating a difference value between a reward value of a current initial noise distribution generated image and a reward value of an original standard normal distribution generated image after the diffusion model outputs the generated image every time, and taking the difference value as a relative reward value; constraining the updating process of the distribution parameters by adopting a proportional clipping algorithm; and calculating a parameter updating step length based on a gradient estimation result, and carrying out proportional clipping on the updating step length. The method is used for improving the consistency of content and prompt semantics in a text-to-image generation task by optimizing the initial distribution parameters of the diffusion model, and meanwhile, the generation quality and the calculation efficiency are kept.

The invention discloses a robot group detection scheduling method and system, and relates to disaster monitoring: scene reconstruction is carried out according to collected real-time sensing information, a three-dimensional digital model of a disaster scene is generated, and a discrete monitoring grid based on sampling points is established; constructing a disaster risk assessment model on the discrete monitoring points, and for gas and fire, calculating the risk value of each monitoring point by using actual measurement data to form a discrete risk distribution map; calculating the space change trend of the risk degree by adopting an adjacent point difference method, and calculating a directed gradient through the risk degree difference value and the distance of adjacent monitoring points; when the risk degrees of any two disasters are increased at the same time, marking the risk points as potential coupling risk points; identifying a propagation path of the risk degree based on connectivity analysis of the monitoring network; and scheduling the robot group by adopting a risk avoiding path planning algorithm. According to the method, the spatial distribution and evolution trend of the disaster field are accurately reconstructed through local gradient estimation under the sparse sampling condition.

The invention belongs to the technical field of neural network model training optimization, and discloses a low-rank matrix gradient estimation method and system for large-scale neural network training, and the method comprises the steps: sampling a low-rank random subspace meeting the equidistant or isotropic constraint based on a preset sampling rule; a matrix gradient estimation algorithm is embedded into the low-rank random subspace to be executed, and accumulation and updating are carried out on low-dimensional auxiliary variables; when the low-dimensional auxiliary variable is accumulated to a preset step number, performing inertia updating on parameters of a matrix gradient estimation algorithm; and calculating a weighting matrix based on all parameters of the matrix gradient estimation algorithm after inert updating, and optimizing a preset sampling rule of a next round of low-rank random subspace according to spectrum information of the weighting matrix so as to realize gradient estimation of the low-rank matrix. According to the method, a scheme including estimation stage low-rank, projection distribution optimization and inertia updating is provided, the video memory and step time threshold is remarkably reduced in engineering, and considerable cost performance is embodied in large model fine tuning.

The invention discloses a fine tuning system of a large-scale pre-training model in a federated learning environment and application thereof. The system comprises a local disturbance gradient estimation module, a differential privacy protection module and a global model aggregation and update module. The local disturbance gradient estimation module is used for calculating a global model loss value by combining forward propagation with a zero-order optimization method so as to estimate a gradient and realize all-parameter fine tuning; the differential privacy protection module performs differential privacy protection processing on the estimated disturbance gradient to prevent gradient information from leaking user sensitive data; and the global model aggregation and update module reconstructs a disturbance vector and completes global model update based on a random seed and a scalar gradient uploaded by a client. Compared with the prior art, on the premise of not depending on back propagation, all-parameter fine tuning of a large-scale pre-training model is achieved, data privacy is guaranteed, meanwhile, calculation and memory expenses are remarkably reduced, and the method is suitable for a resource-limited distributed calculation environment.

The invention relates to the field of artificial intelligence security, and provides an adversarial sample optimization method and device, equipment and a program product. The method comprises the following steps: acquiring an audio sample; according to the audio sample, obtaining a candidate sample by using a preset genetic algorithm; and according to the candidate sample, performing sparse gradient estimation in combination with the target model, and optimizing the candidate sample in combination with a sparse gradient estimation result. According to the confrontation sample optimization method provided by the invention, the acquired audio sample is globally searched by using the preset genetic algorithm to find the closest candidate sample and avoid falling into a locally optimal solution, and sparse gradient estimation is combined to more accurately capture the key decision boundary of the target model, so that a more effective confrontation sample can be generated, and the accuracy of the confrontation sample optimization is improved. Meanwhile, unnecessary disturbance is avoided, the optimization pertinence is improved, the real-time requirement is met, the calculation overhead is reduced, and the optimization efficiency is improved.

A road surface gradient estimation device includes an acquisition unit that acquires each of detection results of an acceleration detection unit that detects an acceleration in a front-rear direction of a vehicle, and a wheel speed detection unit, and acquires information regarding power for driving the vehicle, a derivation unit that derives a gradient of a road surface on which the vehicle is traveling as a first road surface gradient based on the acquired acceleration and wheel speed, and a correction unit that corrects the derived first road surface gradient based on the information regarding the power for driving the vehicle to derive a second road surface gradient.

A system, method, and computer program product for training a generative language model (GLM) is provided. A plurality of sampled rationales for various question-answer pairs are generated using the GLM. A gradient estimate of parameters of neurons in the GLM is determined based on these sampled rationales to maximize the learning objective of the GLM. The parameters of the GLM are modified using the gradient estimate over multiple iterations, ultimately providing a trained GLM.

To reduce the processing load required to recognize the external environment surrounding the vehicle. [Solution] The external environment recognition device 50 includes an on-board detector 5, a recognition unit 111 that recognizes the road surface and three-dimensional objects on the road on which the vehicle is traveling as road surface information based on point cloud data for each frame acquired by the on-board detector 5, a determination unit 113 that determines the interval of detection points necessary for the point cloud data of the next frame based on the size of a predetermined three-dimensional object set in advance as a recognition target and the measured distance from the vehicle to the three-dimensional object based on the point cloud data, and a gradient prediction unit 114 that predicts the gradient of the road surface not recognized by the recognition unit 111 based on gradient information associated with map information on which the road is recorded. The determination unit 113 further determines the interval of detection points necessary for the point cloud data of the next frame based on the size of a predetermined three-dimensional object, the map information and the estimated distance from the vehicle to the three-dimensional object estimated from the gradient, for a range from the furthest distance to the required distance.

The application discloses a black box optimization gradient estimation method and device based on Rung-Kutta extrapolation and a medium, the method of which comprises the following steps: obtaining a target function to be optimized and a gradient solving reference point corresponding to the target function; configuring gradient calculation related parameters, generating a multi-scale step set and a unit orthogonal perturbation vector set based on the gradient calculation related parameters; determining perturbation positions of the target function under different steps based on the gradient solving reference point, the multi-scale step set and the unit orthogonal perturbation vector set, and converting response data corresponding to each perturbation position into numerical differential data; weighting and fusing the numerical differential data corresponding to different scale steps based on a preset fusion weight; then performing correlation processing on each unit orthogonal perturbation vector to obtain multiple gradient components, and obtaining a final gradient estimation result after aggregation processing of each gradient component. According to the application, the Rung-Kutta extrapolation technology is used to systematically offset low-order truncation errors, and the gradient estimation precision is significantly improved.

The application relates to a fast wideband signal detection method, device and equipment based on a time-frequency graph and a medium. The method determines the starting and ending frequencies of a wideband signal by performing Gaussian blurring, time domain averaging, gradient estimation and gradient matching on a time-frequency graph of an electromagnetic signal; verifies and scores the starting and ending frequency positions of each row on the time-frequency graph, and if the score passes, the row contains a wideband signal, otherwise, the row does not contain a wideband signal; determines whether the wideband signal is a continuous signal, and if it is not, calculates the starting and ending times of a wideband signal pulse in the time-frequency graph according to the number of rows containing the wideband signal; and obtains the characteristics of the wideband signal in the time-frequency graph according to the starting and ending frequencies of the wideband signal and the starting and ending times of the wideband signal pulse. The method proposes different feature extraction processes and detection decision mechanisms, guarantees the timeliness of detection, and provides theoretical support for fast wideband signal detection in complex environments.

The invention relates to an automatic focus following method for a microscope, relates to the technical field of microscope imaging, and aims to construct a defocus distance prediction model by taking focusing as a regression problem so as to directly predict a defocus distance based on a picture. In the initial stage of focusing search, a gradient estimation algorithm without global scanning is provided based on a defocus distance prediction model, and the optimal focal plane is quickly converged through the adjustment steps of detecting a current area, predicting a focusing position, jumping to the focusing position and using the least imaging times and the least camera height, so that the focusing time is remarkably shortened, and the focusing efficiency is improved. The technical problems that an existing focusing algorithm is large in operand, and focusing to a wrong position is prone to occurring are solved.

This application belongs to the field of visual compensation technology and provides a visual compensation method under starlight conditions. Through pre-sampling and grayscale variance statistics, it achieves the determination of starlight compensation intervals and the dynamic division of target and background regions in the imaging plane. It adopts a sampling method with different exposure time series for the target and background regions to obtain multiple frames of original sampled data and pixel integration time. Based on the pixel integration time, it constructs a spatially variable gain matrix and completes inter-frame registration and gain normalization processing to separate signal and noise components in the image. The signal component is used as a sparse sampling stream, and the pixel variance distribution of the noise component is used as a hyperparameter of the variational inference algorithm. Image reconstruction is completed through probability density gradient estimation, making the variational inference process match the actual noise distribution characteristics under starlight conditions, thereby improving the quality and reliability of visual imaging under starlight conditions.

The application discloses a kind of federal reinforcement learning method and system based on hessian auxiliary and strategy gradient under heterogeneous environment, including server and multiple clients, server initializes global model parameter, global gradient update quantity and global control variable and broadcasts to client, client takes current global model parameter as local update starting point, obtains main trajectory and hessian estimation auxiliary trajectory by parameter interpolation and double trajectory sampling, constructs hessian auxiliary correction term at interpolation parameter, and forms local gradient estimation in combination with control variable correction term, uploads parameter update quantity and control variable update quantity after completing multi-step local update, server aggregates each client upload result, updates global model parameter and global control variable, and outputs global strategy model parameter after cyclic iteration, completes federal reinforcement learning.The application can weaken the client drift caused by heterogeneous environment, reduce strategy gradient estimation fluctuation, improve training stability and global strategy performance.

The invention discloses a navigation method, device and equipment based on a GRPO algorithm and a medium, and relates to the technical field of reinforcement learning, and the method comprises the steps: calculating the average similarity between a current strategy and a plurality of previous iteration strategies based on KL divergence; updating a step length factor through an average reward change rate and an average similarity determined based on a plurality of iterated rewards; determining a gradient estimation correction item based on the gradient estimation of the sampling trajectory, determining target gradient estimation according to the gradient estimation correction item and the original gradient estimation, and updating the current strategy through the target gradient estimation and the updated step length factor; when the current strategy is updated, the importance weight is cut, the target function of the GRPO algorithm is corrected according to the cut weight, the GRPO algorithm is trained based on the corrected function and the updated strategy, so that the intelligent agent learns the optimal strategy based on the trained GRPO algorithm, and the outlet of the labyrinth is determined according to the optimal strategy. Therefore, the stability of the algorithm is improved.

A quantum circuit is configured to implement a quantum gradient algorithm when executed on qubits of a quantum computing system. The quantum gradient algorithm includes a phase oracleOSfmdefined by a finite difference approximation with an order greater than zero, and a complexity of the quantum gradient algorithm scales as (√{square root over (k)} / ϵ). The quantum circuit is repeatedly executed on qubits of a quantum computing system to determine a k-dimensional gradient of a function ƒ(x) within an error ϵ at point x0, where ƒ(x) is not a Gevrey class G1 / 2 function.

The invention belongs to the technical field of model fine tuning, and discloses a post-training fine tuning method and system for a diffusion model, and the method comprises the steps: carrying out the recursive structure analysis of a pre-obtained diffusion model based on a recursive likelihood ratio optimizer, obtaining recursive parameters, and determining the generation condition of the diffusion model through multi-scale prompt information; according to recursion parameters and generation conditions of the diffusion model, parameters are injected in the recursion process of the diffusion model, and the gradient of the diffusion model is estimated in combination with a gradient estimation method; and according to the estimated gradient of the diffusion model, updating parameters of the diffusion model by utilizing a model parameter updating formula so as to realize post-training adjustment of the diffusion model. The method has the characteristics of lower variance and higher sample efficiency, and effectively reduces the variance of gradient estimation by combining zero-order, half-order and first-order gradient estimation technologies.

The application provides a terahertz SAR high-efficiency self-focusing imaging method and system based on RB-PCA, comprising: obtaining original echo signal data and performing pretreatment; performing distance block in the distance direction on the pretreated echo signal data to obtain a plurality of distance blocks, performing sub-aperture segmentation in the distance block for each distance block to obtain a plurality of sub-aperture signal data; performing desquamation processing on each sub-aperture signal data to obtain desquamation signal data; performing PCA processing on the desquamation signal data and selecting a characteristic vector with the largest characteristic value as a target characteristic vector; obtaining each sub-aperture phase error gradient estimation value through adaptive PGA estimation on the target characteristic vector; obtaining two-dimensional space-varying phase errors of each distance block through global splicing and fusion on each sub-aperture phase error gradient estimation value; and performing phase compensation and azimuth compression on the pretreated echo signal data based on the two-dimensional space-varying phase errors to obtain focused imaging results.

The invention provides a gradient-based black box face deep counterfeiting watermarking resisting method, equipment and a medium, and relates to the technical field of image processing. The method comprises the following steps: acquiring an original face image, and inputting the original face image into a forward noise adding process of a denoising diffusion implicit model to obtain a noise potential variable in the step; and taking the variable as an initial denoising starting point for resisting watermark generation, executing a reverse denoising process of the denoising diffusion implicit model, and estimating a loss gradient corresponding to the depth forgery model under the setting of a black box by adopting a gradient estimation method based on a natural evolution strategy in each denoising process. And weighting the loss gradient and a preset guide weight, and then superposing the weighted weight to the denoised image in the current denoising step to generate an intermediate confrontation face image in the current denoising step. And continuously iterating the middle confrontation face image based on each de-noising step until all de-noising steps are completed, and obtaining a final confrontation face image.

The application discloses a kind of based on gradient estimation joint optimal solution search underwater acoustic OFDM system carrier synchronization algorithm, belong to underwater acoustic communication technical field.The specific method includes the following steps: step one: in underwater acoustic OFDM communication system, time domain method is used to underwater acoustic OFDM carrier synchronization.Step two: in an OFDM frame, first OFDM symbol is estimated based on optimal solution search carrier synchronization algorithm to carry out frequency offset estimation.Step three: from the second OFDM symbol, gradient descent-based carrier synchronization algorithm is used to estimate frequency offset value, and the frequency offset estimation result of the first OFDM symbol is used as the initial value of iteration.The present application can carry out more fine residual carrier frequency offset compensation by pilot symbol, improve the step of underwater acoustic system carrier synchronization algorithm using Adam method, reduce complexity while improving accuracy, realize reliable and effective underwater acoustic OFDM communication.

The invention provides a model generation method and device, a marketing text generation method and device and network device.The model generation method for generating marketing texts comprises the steps that historical marketing texts are obtained, and a training data set is generated; performing noise addition processing on original data in the training data set to generate first data; according to the dominant function, diffusion denoising processing is carried out on the first data step by step through a diffusion model, in the denoising processing process, the diffusion model is updated based on gradient calculation until convergence is achieved every a first number of diffusion steps, and a target model used for generating a marketing text is obtained, the diffusion model is used for carrying out denoising processing on the first data according to the strategy network, and in each diffusion step, the dominant function is used for reducing gradient estimation variance of strategy network parameters by evaluating relative advantages of denoising actions in a current state. The marketing text generated by adopting the target model is high in accuracy and high in adaptability, so that the marketing effect is remarkable.

The invention relates to a switchable activation network reasoning method and device based on dynamic gating and a medium. The method comprises the following steps: firstly, inputting input data in a training data set into a first neural network, and calculating a first activation result through a learnable soft gating function; then, in combination with a label corresponding to the first activation result, a through gradient estimator is adopted, a preset loss function is minimized through back propagation, and a second neural network is obtained; the preset loss function comprises a target loss function and a multi-dimensional constraint, so that the second neural network is balanced between precision and efficiency. Then, processing the second neural network based on a hard gating function inheriting gating parameters of the soft gating function to obtain a third neural network; and inputting to-be-processed test data into the third neural network, and outputting a prediction result corresponding to the test data. Therefore, the balance between the efficiency and the precision can be realized when the deep neural network performs efficiency optimization.

The invention relates to a distributed database parameter adaptive tuning method based on multi-agent deep reinforcement learning, and belongs to the technical field of information. According to the method, the thought of a multi-agent deep reinforcement learning algorithm is introduced into the field of database parameter tuning, the cooperation and competition relation between nodes in a distributed database environment is explored, and a deep deterministic strategy gradient reinforcement learning algorithm C-MADDPG based on a centralized strategy gradient estimator is provided. A distributed database parameter tuning problem is modeled based on a partially observable Markov decision process. Problem definition takes expansion of a parameter search space as a cost, takes a complex competition effect between database nodes as a black box, carries out mathematical modeling on an observable cooperation effect, improves the universality and scalability of an algorithm, solves a relative generalization problem of the algorithm, and can be expanded to a general distributed database architecture. The C-MADDPG provided by the invention shows good performance in the parameter tuning of the distributed database.

The invention discloses a hovercraft and a parameter integrated design method, device and equipment thereof, and the method comprises the steps: fixing the basic structure parameters of a propeller of the hovercraft, and randomly sampling the strategy hyper-parameters of different controllers on the basis of the basic structure parameters; executing the navigation task in the simulation environment based on different performance costs to obtain corresponding performance costs; a self-adaptive optimization method based on historical gradient estimation is adopted to analyze the variation trend with the system performance, and iterative updating is carried out according to the variation trend until the performance cost numerical value is converged, so that an optimal strategy hyper-parameter is obtained; fixing of the basic structure parameters is relieved, the basic structure parameters and the basic structure parameters jointly form a design vector, the optimal strategy hyper-parameters serve as the benchmark, a two-stage Bayesian optimization strategy is adopted to conduct collaborative search on the design vector, and a global optimal design vector is obtained; and carrying out integrated design of the hovercraft based on the optimal design vector.

According to one aspect of the present disclosure, a method of image processing and a computer-readable medium are provided. The method may include: inputting a first color image and a first depth image into a gradient-estimation network, performing gradient-estimation of the first color image and the first depth image using the gradient-estimation network to generate first depth-edge information, inputting a second depth image and the first depth-edge information into a depth-upsampling network, performing depth upsampling of the second depth image using the first depth-edge information to generate second depth-edge information, inputting the first depth-edge information and the second depth-edge information into a fusion network, fusing the first depth-edge information and second depth-edge information using the fusion network to generate a residual map, and combining the first depth image and the residual map to generate a third depth image.